Concept Drift Detection and Model Selection with Simulated Recurrence and Ensembles of Statistical Detectors.
Piotr SobolewskiMichal WozniakPublished in: J. Univers. Comput. Sci. (2013)
Keyphrases
- model selection
- concept drift
- statistical inference
- ensemble learning
- cross validation
- data streams
- change detection
- non stationary
- machine learning
- hypothesis tests
- data distribution
- feature selection
- multivariate regression
- statistical methods
- sample size
- information criterion
- variable selection
- gaussian process
- model selection criteria
- classification algorithm
- unsupervised learning
- decision trees
- marginal likelihood
- selection criterion
- sliding window
- similarity measure
- bayesian networks
- face recognition
- bayesian information criterion
- support vector
- data analysis
- image registration
- learning algorithm